Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.16 | $0.15 | per 1M tokens |
| Outputper 1M tokens | $0.32 | $0.29 | per 1M tokens |
The price per million tokens, by day.
Today · $0.16 in · $0.32 out per 1M tokens
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| KT, answering | 99.9% | 262K |
| CoreWeaveFp4fp4, answering | 100% | 262K |
| VeniceFp4fp4, answering | 100% | 256K |
| ChutesFp4fp4, answering | 99.3% | 131K |
| DeepInfraTurbofp4, answering | 100% | 262K |
| DekaLLM, answering | 99.2% | 262K |
| CrusoeBf16bf16, answering | 99.9% | 262K |
| Friendli, answering | 100% | 262K |
| NovitaBf16bf16, answering | 92.9% | 262K |
| NextBitFp4fp4, answering | 100% | 262K |
| ParasailFp8fp8, answering | 100% | 262K |
| DeepInfraFp8fp8, answering | 100% | 262K |
| PrimeIntellectFp4fp4, answering | 99.9% | 262K |
| DeepInfraFp8fp8, answering | 100% | 262K |
| DeepInfraFp8fp8, having trouble | 99% | 262K |
| Modal, answering | 100% | 131K |
| SambaNova, having trouble | 84.7% | 131K |
| SiliconFlowFp8fp8, answering | 98.9% | 262K |